© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 17971
    Prev
    Next
    INDEX
    Explanations

    questions and advice

    np_max-act · gemini-2.0-flash

    first-person, problem-focused requests for practical guidance—often urgent, safety/health-related, and expressing worry about what to do next.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respects
    -0.07
    CDF
    -0.06
    Cri
    -0.06
    Islam
    -0.06
    现实
    -0.06
     acciones
    -0.06
    metics
    -0.06
    .Sin
    -0.06
    sense
    -0.06
    专业技术
    -0.06
    POSITIVE LOGITS
    ƙ
    0.07
    烟囱
    0.07
    Gate
    0.07
    ◻
    0.07
     Images
    0.07
    /bar
    0.07
    翦
    0.07
     gust
    0.07
    _GUID
    0.07
     Smile
    0.07
    Activations Density 0.028%

    No Known Activations